/* --------------------------Exercise 11.6 & 12.6 ------------------------------------------------- */

data sg.MN_116;
input MPG @@;
datalines;
24 14 25 30 28 26 32 28 28 34 27 26 23 24 28 34 29 23 26 26 27 24 25 27 27 28 19 28 29 28 28 
;
proc print;
run;

/*filename odsout 'C:\Documents and Settings\nahtman\Mina dokument\t2.htm';
ods listing close;
ods html file=odsout style=gears;*/
 
/*proc univariate data=MN_116; 
 histogram mpg / cframe = ligr cfill  = blue; 
run; */
 
*ods select HistogramBins MyHist; 
title 'The highway fuel consumption (midsize cars)'; 

ods html;
proc univariate data=sg.MN_116; 
histogram mpg / /*midpercents*/vscale=percent 
VAXIS=(0 10 20 30 40 60) /*midpoints = 16 to 32 by 4*/ endpoints=14 to 32 by 4 ; 
run; 
ods html close;
 
ods html;
proc univariate plot data=sg.MN_116 noprint; 
histogram mpg / midpercents VREF = (5 10 15) vscale = count VAXIS=(0 5 10 15 20) midpoints = 16 to 32 by 4; 
run; 
ods html close;

/*  
title 'The highway fuel consumption (midsize cars)'; 
proc univariate data=MN_116; 
histogram mpg / midpoints = 15 to 33 by 2 rtinclude; 
run; 

PROC UNIVARIATE PLOT data=MN_116 PLOTSIZE=34; 
VAR mpg; 
RUN; 
*/

goptions reset=all; 

/*ods html close;
ods listing;*/

/* --------------------------- 11.8 ----------------------------------------- */

data sg.MN_118;
input salary;
datalines;
22000000
18600000
16000000
15714286
13000000
12428571
12357142
10890000
9000000
9000000
8500000
7000000
6000000
3100000
3000000
2700000
2000000
1925000
1800000
1000000
900000
775000
750000
700000
500000
450000
302550
301400
;
*proc print;
*run;

title 'Salaries of the New Yourk Yankees, 2004'; 
/*ods html;
proc univariate data=sg.MN_118; 
histogram salary / cframe = ligr cfill  = blue; 
run; 
ods html close;*/

ods html;
proc univariate data=sg.MN_118; 
 histogram salary/ midpercents endpoints = 0 to 22000000 by 4000000; 
run; 

proc univariate data=sg.MN_118; 
histogram salary / midpoints    = 1000000 to 21000000 by 4000000 rtinclude; 
run; 
ods html close;
*goptions reset=all; 

/* --------------------------------------------------------------------------- */

data sg.MN_119; 
input length percent; 
i=_N_;
x=10*percent;
datalines; 
1	3.6 
2	14.8 
3	18.7 
4	16 
5	12.5 
6	8.2 
7	8.1 
8	5.9 
9	4.4 
10	3.6 
11	2.1 
12	0.9 
13	0.6 
14	0.4 
15	0.2
; 

title 'Distribution of the lengths of words';
proc freq data=sg.MN_119;
weight x;
tables length/ out=ord OUTCUM;
run;
proc print;

proc univariate data=ord; 
freq count;
histogram length / /*cframe = blue*/ cfill  = ligr; 
run; 

/* 
symbol interpol=join l=1 w=2;
proc gplot data = ord; 
plot cum_pct*length/ vref=50; 
run;
quit;

goptions reset = all;ods html close;*/

/* --------------------------------------------------------------------------- */

data sg.MN_1114;
input age_group year_1950 year_2075;
datalines;
1 29.3	34.9
2 21.8	35.7
3 24	36.8
4 22.8	38.1
5 19.3	37.8
6 15.5	37.5
7 11	34.5
8 5.5	27.2
9 1.6	18.8
10 0.1	7.7
11 .	1.7
;

proc freq data=sg.MN_1114;
weight year_1950;
tables age_group/ out=FreqCnt;
title1 'Age distribution in the Unated States. 1950 and 2075';
run;

/*proc print data=FreqCnt noobs;title2 'Output Data Set from PROC FREQ';run;*/

proc freq data=sg.MN_1114;
weight year_2075 ;
tables age_group/ out=FreqCnt1 outexpect sparse;
title1 'Age distribution in the Unated States. 1950 and 2075';
run;

/*proc print data=FreqCnt1 noobs;title2 'Output Data Set from PROC FREQ';run;*/

/*title 'Age distribution in the Unated States. 1950'; 

proc univariate data=FreqCnt; 
freq count;
histogram age_group / cframe = ligr cfill  = blue; 
run; 
 
proc univariate data=FreqCnt; 
freq count;
histogram age_group/ midpercents cframe = ligr cfill = blue endpoints = 1 to 11 by 1; 
run;*/ 

ods html;
title 'Age distribution in the Unated States, 1950'; 

proc univariate data=FreqCnt; 
freq count;
histogram age_group/ midpoints = 1 to 10 by 1 rtinclude; 
run; 

title 'Age distribution in the Unated States, 2075'; 

proc univariate data=FreqCnt1; 
freq count;
histogram age_group / /* cframe = ligrcfill  = blue*/ VAXIS=(0 2.5 5 7.5 10 12.5 15 17.5 20); 
run; 

ods html close;

/* --------------------------Exercise 11.9 ------------------------------------------------- */

data sg.MN_119; 
input ord percent; 
i=_N_;
x=10*percent;
datalines; 
1	3.6
2	14.8
3	18.7
4	16
5	12.5
6	8.2
7	8.1
8	5.9
9	4.4
10	3.6
11	2.1
12	0.9
13	0.6
14	0.4
15	0.2
; 
proc print;
   run; 

proc freq data=sg.MN_119;
weight x;
tables ord/ out=ord outexpect sparse;
title1 'Distribution of the lengths of words';
run;proc print;

proc univariate data=ord; 
freq count;
histogram ord / cfill  = ligr; 
run; 

/* --------------------------Exercise 12.9 ------------------------------------------------- */

data sg.MN_129;
input calories;
datalines;
173
191
182
190
172
147
146
139
175
136
179
153
107
195
135
140
138
;

ods html ;
PROC UNIVARIATE PLOT data=sg.MN_129 ; 
VAR calories; 
RUN;
 
ods html close;

/* --------------------------Exercise 12.12 ------------------------------------------------- */

/* 
data sg.MN_1212;
input p ord;
count=p*10;
datalines;
3.6	1
14.8	2
18.7	3
16	4
12.5	5
8.2	6
8.1	7
5.9	8
4.4	9
3.6	10
2.1	11
0.9	12
0.6	13
0.4	14
0.2	15
;
run;

goptions reset=all gunit=pct border cback=white colors=(black blue green red) ftitle=swissb ftext=swiss htitle=5 htext=3.5;

/* Define title 
title1 'The statistics of writing styles';
footnote h=3 j=r 'Moore & Notz';

/* Modify axes 
axis1 label=('The lengths of words' j=c) minor=(number=1);
axis2 label=('Percent' j=r 'Group');

/* Define pattern characteristics 
pattern1 color=cyan;

proc gchart data=sg.MN_1212;
*vbar ord/freq=count sumvar=p NOZERO;
*block ord/NOHEADING freq=count sumvar=p midpoints= 1 to 15 by 1 ;
run ;
quit;
*/

/* ------------------------Exercise 12.20 ------------------------------------- */

data sg.MN_1220;
input mpg;
datalines;
21
19
18
18
18
19
22
18
21
19
21
21
20
20
16
17
17
23
18
19
19
20
27
22
27
21
;

ods html;
title 'The highway fuel consumption (SUV)'; 

PROC UNIVARIATE data=sg.MN_1220 PLOTSIZE=27; 
histogram mpg / midpercents  VAXIS=(0 10 20 30 40 50 60) endpoints = 14 to 34 by 4 rtinclude ;
*VAR mpg; 
RUN; 
PROC UNIVARIATE PLOT data=sg.MN_1220 PLOTSIZE=27; 
histogram mpg / midpercents vscale=percent VAXIS=(0 5 10 15 20) /*endpoints = 14 to 34 by 4*/midpoints=16 to 36 by 4 rtinclude ;
*VAR mpg; 
RUN; 
ods html close;

title 'The highway fuel consumption (SUV)';
ods select BasicMeasures Quantiles;
proc univariate data=sg.MN_1220;
var mpg;
run;

title 'The highway fuel consumption (midsize cars)';
ods select BasicMeasures Quantiles;
proc univariate data=sg.MN_116;
var mpg;
run;

Data sg.MN_MPG;
set sg.MN_116 sg.MN_1220;
size='Midsize';
if _N_>31 then size='SUV';
proc print;
run;


ods html style=gears;

proc means data=sg.MN_MPG mean q1 median q3 min max;
var mpg;
by size;
run;

ods graphics on;

symbol1 v=plus     c=salmon;
symbol2 v=square   c=vigb;
symbol3 v=triangle c=vig;
title 'MPG (The highway fuel consumption, miles per gallon)';
   proc boxplot data=sg.MN_MPG;
      plot MPG*size / cboxes = dagr cboxfill = ywh cframe = vligb;
 *     inset / height=6 cfill=ywh header='Midsize cars: 26.6' pos=w ;
*inset mean / pos = ne format = 6.3 cfill = ywh;

      label MPG = 'Fuel consumption';
	  label size = 'Car size';

   run;

   ods graphics off;
   ods html close;

data iu1;
set sg.inuppgift2;
proc print;
run;

proc sort data=iu1;
by opinion;
run;

ods html;
proc univariate data=iu1; 
class opinion;
histogram age /vscale=count cfill  = blue cframe = ligr endpoints = 20 to 50 by 5; 
inset n mean; 
run; 
ods html close;